3 citations · 8 across the 7 of their papers we have counts for
8 papers
Decom-Renorm-Merge: Model Merging on the Right Space Improves Multitasking
Yuatyong Chaichana, Thanapat Trachu, Peerat Limkonchotiwat +3
In the era of large-scale training, model merging has evolved into a tool for creating multitasking models efficiently. It enables the knowledge of models to be fused, without the…
Accelerating Blockchain Scalability: New Models for Parallel Transaction Execution in the EVM
Souradeep Das, Konpat Preechakul, Jonas Bäumer +2
As the number of decentralized applications and users on Ethereum grows, the ability of the blockchain to efficiently handle a growing number of transactions becomes increasingly s…
Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting
Anand Bhattad, Konpat Preechakul, Alexei A. Efros
This paper proposes a novel scene understanding task called Visual Jenga. Drawing inspiration from the game Jenga, the proposed task involves progressively removing objects from a…
Optimizing Diffusion Noise Can Serve As Universal Motion Priors
Korrawe Karunratanakul, Konpat Preechakul, Emre Aksan +3
We propose Diffusion Noise Optimization (DNO), a new method that effectively leverages existing motion diffusion models as motion priors for a wide range of motion-related tasks. I…
Guided Motion Diffusion for Controllable Human Motion Synthesis
Korrawe Karunratanakul, Konpat Preechakul, Supasorn Suwajanakorn +1
Denoising diffusion models have shown great promise in human motion synthesis conditioned on natural language descriptions. However, integrating spatial constraints, such as pre-de…
Diffusion Autoencoders: Toward a Meaningful and Decodable Representation
Konpat Preechakul, Nattanat Chatthee, Suttisak Wizadwongsa +1
Diffusion probabilistic models (DPMs) have achieved remarkable quality in image generation that rivals GANs'. But unlike GANs, DPMs use a set of latent variables that lack semantic…
High resolution weakly supervised localization architectures for medical images
Konpat Preechakul, Sira Sriswasdi, Boonserm Kijsirikul +1
In medical imaging, Class-Activation Map (CAM) serves as the main explainability tool by pointing to the region of interest. Since the localization accuracy from CAM is constrained…
CProp: Adaptive Learning Rate Scaling from Past Gradient Conformity
Konpat Preechakul, Boonserm Kijsirikul
Most optimizers including stochastic gradient descent (SGD) and its adaptive gradient derivatives face the same problem where an effective learning rate during the training is vast…